Cyberbullying Detection and Severity Determination Model

Abstract

Some teenagers actively participate in cyberbullying, which is a pattern of online harassment of others. Many teenagers are unaware of the risks posed by cyberbullying, which can include depression, self-harm, and suicide. Because of the serious harm it can cause to a person's mental health, cyberbullying is an important problem that needs to be addressed. This research aimed to develop a technique to identify the severity of bullying using a deep learning algorithm and fuzzy logic. In this task, Twitter data (47,733 comments) from Kaggle were processed and analyzed to flag cyberbullying comments. The comments embedded by Keras were fed into a long short-term memory network, composed of four layers, for classification. After that, fuzzy logic was applied to determine the severity of the comments. Experimental results suggest that the proposed framework provides a suitable solution to detect bulling with values of 93.67%, 93.64%, 93.62% achieved for the accuracy, F1-score, and recall, respectively.INDEX TERMS Deep learning algorithm, severity of bullying, LSTM.

Deep Learning Algorithms for Cyber-Bulling Detection in Social Media Platforms

“…The final set of tests is performed to compare the difficulty of the proposed system. In other terms, the utilization of computer resources by a program is explored using the same citations as discussed in our prior publication [7]. The duration taken for one complete cycle of the dataset in question is detailed in Table 5 within this investigation, which showed that the required times were 493 sec, 21 sec, and 814 sec for Twitter, Instagram, and Facebook, respectively.…”

“…The study presents the creation of an LSTM deep learning detection model capable of identifying cyberbullying content in user comments across three distinct social media platforms in real-time. The experimental setup for the new dataset closely follows the methodology outlined in a prior publication [7]. in an attempt to solve the limitation, allowing us to examine how well the suggested model performs on the chosen datasets and how adaptable it is to other datasets.…”

Comparative Analysis of Word Embeddings for Multiclass Cyberbullying Detection

“…The study [18] involves the utilization of a deep learning algorithm in conjunction with fuzzy logic to analyze 47,733 comments from Twitter, obtained from Kaggle. The methodology includes processing these comments using Keras embeddings and classifying them with a four-layer LSTM network.…”

Attribute-specific Cyberbullying Detection Using Artificial Intelligence

“…(2024) [17] proposed a method using a CNN to detect cyberbullying incidents on Instagram, demonstrating the capacity of deep learning models to discern intricate patterns in multimedia-rich content. Long Short-Term Memory (LSTM) networks, a type of RNN, have been employed for sequential modeling, enabling the understanding of temporal dynamics in cyberbullying conversations [18] . Deep learning models showcase a high degree of sophistication in understanding context and semantics, making them well-suited for cyberbullying detection tasks.…”